GitHub
reflexion
Record feedback on pattern effectiveness. Stores episodes that train the recommendation system and enable pattern discovery via learner.
☆ 0查看技能
tools machine learning AI 技能
发现 tools machine learning 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
分类目录: tools machine learning
tools machine learning 清除筛选
全部技能
GitHub
feature-extraction
Extracts vector embeddings for fairness analysis using MobileNetV3 with FairDisCo disentanglement
☆ 0查看技能
GitHub
calibration
Applies decision thresholds for high-confidence inputs or enforces conservative safety margins for low-confidence cases
☆ 0查看技能
GitHub
lesion-detection
Classifies skin conditions including Melanoma and Basal Cell Carcinoma using TF.js MobileNetV3
☆ 0查看技能
GitHub
agent-workflow-builder-ai-toolkit
Expert in streamlining and enhancing the development of AI Agent Applications, including AI app / agent / workflow code generation, AI model comparison and recommendation, tracing setup, and evaluation planning...
☆ 0查看技能
GitHub
ai-integration
Integrating AI and LLM capabilities into applications for enhanced functionalities. Use when implementing AI features, processing data with ML models, building generative workflows, or integrating AI APIs.
☆ 0查看技能
GitHub
faion-ml-engineer
ML Engineer role: LLM APIs (OpenAI, Claude, Gemini), embeddings, RAG pipelines, fine-tuning, LangChain, LlamaIndex, vector databases (Pinecone, Chroma, Weaviate), prompt engineering, model evaluation, cost opti...
☆ 0查看技能
GitHub
east-py-datascience
Data science and machine learning platform functions for the East language (TypeScript types). Use when writing East programs that need optimization (MADS, Optuna, SimAnneal, Scipy), machine learning (XGBoost,...
☆ 0查看技能
GitHub
speckit-specify
Create or update the feature specification from a natural language feature description.
☆ 0查看技能
GitHub
workers-ai
Cloudflare Workers AI の完全ガイド。利用可能モデル（LLM、画像、音声、埋め込み）、Vectorize、AI Gateway の使い方と設定を提供。Use when user asks about Workers AI, AI models, Vectorize, AI Gateway, LLM, image gen...
☆ 0查看技能
GitHub
moai-formats-data
Data format specialist covering TOON encoding, JSON/YAML optimization, serialization patterns, and data validation for modern applications. Use when optimizing data for LLM transmission, implementing high-perfo...
☆ 0查看技能
GitHub
data-analysis
Statistical analysis and data exploration workflows for effective data-driven insights. Use when analyzing datasets, performing exploratory data analysis (EDA), statistical hypothesis testing, data visualizatio...
☆ 0查看技能
GitHub
meta-learning
Continuous learning and improvement system for paracle_meta. Use when you need to record feedback, track quality metrics, or improve generation templates over time.
☆ 0查看技能
GitHub
frontier-project
Create new frontier projects that solve unsolved problems in ML/AI tooling. Use when you want to add a genuinely novel project to a playbook or monorepo—not "best practices" collections but real tools for probl...
☆ 0查看技能
GitHub
prediction-tracking
Track and evaluate AI predictions over time to assess accuracy. Use when reviewing past predictions to determine if they came true, failed, or remain uncertain.
☆ 0查看技能
GitHub
langchain
Expert guidance for building LLM applications with LangChain framework - chains, prompts, memory, retrievers, and integrations.
☆ 0查看技能
GitHub
benchmark-onboarder
Onboard AI creativity benchmarks into HELM-compliant Scenario implementations. Use when asked to onboard a benchmark, create a HELM scenario, process a paper into evaluation code, convert a dataset to HELM form...
☆ 0查看技能
GitHub
rl-training
Reinforcement learning training for CTF-AI. Use when training DQN agents, adjusting hyperparameters, debugging training issues, analyzing rewards, or improving AI performance.
☆ 0查看技能
GitHub
backend-dev
Python backend development for CTF-AI. Use when working on game engine, player logic, pathfinding, WebSocket server, or any backend Python code.
☆ 0查看技能
GitHub
workflow-metrics
Track, evaluate, and analyze multi-agent AI workflows using Azure AI Foundry cloud evaluations. Use when logging agent trajectories, computing evaluation metrics, measuring plan adherence, or generating workflo...
☆ 0查看技能
GitHub
plan-mode-arc-gsm8k-improvement
AEGISモデルのARC-Challenge評価改善とGSM8K健全性チェックのためのPlanモード。タイムアウト率・抽出失敗率分析、頑健な回答抽出、データ汚染検査、複数seed評価を実行。
☆ 0查看技能
GitHub
plan-mode
AEGISモデルのARC-Challenge改善、GSM8K健全性検証、GRPO報酬多目的化のための包括的Planモード。頑健な回答抽出、タイムアウト最適化、データ汚染チェック、複数seed評価、汎化性能向上を実装。
☆ 0查看技能
GitHub
plan-mode-advanced
Create and execute advanced execution plans for complex AI model development incorporating 2024-2026 cutting-edge techniques (DeepSeek GRPO, manifold-constrained architectures, geometric scaling). Use when plan...
☆ 0查看技能
GitHub
quantization-evaluation-pipeline
Execute GGUF quantization with imatrix protection, perform statistical benchmark evaluation with error bars, generate academic-style methodology documentation, and create comprehensive scorecards. Use when eval...
☆ 0查看技能
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。